shithub: opus

Info  •  Files  •  Log  •  Branches

...

--- a/dnn/lpcnet.py

+++ b/dnn/lpcnet.py

@@ -11,7 +11,7 @@

 import h5py

 import sys

-rnn_units1=256

+rnn_units1=512

 rnn_units2=32

 pcm_bits = 8

 embed_size = 128

--- a/dnn/train_wavenet_audio.py

+++ b/dnn/train_wavenet_audio.py

@@ -111,6 +111,7 @@

 features = np.reshape(features, (nb_frames, feature_chunk_size, nb_features))

 features = features[:, :, :nb_used_features]

+features[:,:,18:36] = 0

 pred = np.reshape(pred, (nb_frames, pcm_chunk_size, 1))

 pred = pred.astype('uint8')

@@ -119,8 +120,8 @@

 in_data = np.concatenate([in_data, pred], axis=-1)

 # dump models to disk as we go

-checkpoint = ModelCheckpoint('wavenet5p0_{epoch:02d}.h5')

+checkpoint = ModelCheckpoint('lpcnet5_512_10_G32np_{epoch:02d}.h5')

 #model.load_weights('wavenet4f2_30.h5')

-model.compile(optimizer=Adam(0.001, amsgrad=True, decay=5e-5), loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])

-model.fit([in_data, in_exc, features, periods], out_data, batch_size=batch_size, epochs=60, validation_split=0.2, callbacks=[checkpoint, lpcnet.Sparsify(1000, 20000, 200, 0.25)])

+model.compile(optimizer=Adam(0.0005, amsgrad=True, decay=5e-5), loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])

+model.fit([in_data, in_exc, features, periods], out_data, batch_size=batch_size, epochs=60, validation_split=0.2, callbacks=[checkpoint, lpcnet.Sparsify(1000, 20000, 200, 0.1)])

-- 

⑨